vllm-project · vLLM · published 2026-06-22
CVE-2026-54236vLLM: incomplete CVE-2026-22778 fix leaks PIL repr addresses via Anthropic router
This month Public proof-of-concept exists (SSVC exploitation: poc).
CVE-2026-54236 has a public proof-of-concept exploit, but no confirmed exploitation in the wild. EPSS estimates a 0.9% chance of exploitation in the next 30 days, higher than 61% of all CVEs. This vLLM vulnerability: CVSS 5.3 (v3.1), attacks can be automated. Fixed upstream in vLLM 0.24.0. Patch in your normal monthly cycle.
Jump to: Remediation Exploit intelAffected versionsDescription
Remediation#
Fixed upstream in vLLM 0.24.0.
Patch events
AI toolingvLLM
vLLM security release: 0.24.0
Upgrade to
0.24.0Why: CVE-2026-54236: Public proof-of-concept exists (SSVC exploitation: poc).
Exploit intelligence#
| Signal | Value | Source |
|---|---|---|
| Known exploited | No | CISA KEV |
| Ransomware use | — | CISA KEV |
| EPSS (30-day exploitation probability) | 0.9% (61th pct) | FIRST EPSS v2026.06.15 |
| CVSS base score | 5.3 (v3.1)CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:N/A:N | CNA / CISA ADP |
| SSVC exploitation | poc | CISA Vulnrichment |
| SSVC automatable | Yes | CISA Vulnrichment |
| SSVC technical impact | partial | CISA Vulnrichment |
Affected versions (from the CVE record)#
- vllm-project vllm
< 0.23.1rc0(affected)
Description (from the CVE record)#
vLLM is an inference and serving engine for large language models (LLMs). Prior to 0.23.1rc0, the fix for CVE-2026-22778, which introduced a sanitize_message helper that strips object-repr memory addresses from error messages before they reach the client, is incomplete: several response paths echo str(exc) directly to clients without calling sanitize_message. The unsanitized sites include the Anthropic API router in vllm/entrypoints/anthropic/api_router.py (the POST /v1/messages and POST /v1/messages/count_tokens handlers), the Server-Sent Events streaming converter in vllm/entrypoints/anthropic/serving.py, and the realtime speech-to-text WebSocket in vllm/entrypoints/speech_to_text/realtime/connection.py. These paths catch the exception inside the route coroutine and construct the JSONResponse themselves, bypassing the sanitizing global FastAPI exception handler, and WebSocket frames do not traverse that handler chain at all. Using the same primitive as the parent issue, an unauthenticated attacker can send malformed image bytes through the Anthropic Messages API image content parts so that PIL.Image.open raises an UnidentifiedImageError whose message contains the BytesIO object repr, leaking the heap memory address verbatim in the error.message field of the response body. This vulnerability is fixed in 0.23.1rc0.
Quoted from the CVE Program record.